gobby-cli

Rust CLI tools for AI-assisted development.
Code search, symbol navigation, output compression, and local LLM launching — all from the terminal.

---

What's Inside

This workspace contains three Gobby CLI tools:

gcode — Code Search & Navigation

AST-aware code search powered by tree-sitter. Indexes 18 languages into SQLite FTS5 for instant symbol lookup, content search, and file tree navigation. With Gobby, adds semantic vector search (Qdrant) and dependency graph analysis (Neo4j) — callers, usages, imports, and blast-radius. Incremental indexing, cross-project queries, and graceful degradation when services are unavailable.

gsqz — Output Compression

Squeezes CLI output before it eats your context window. 28 built-in pipelines for git, cargo, pytest, eslint, ruff, npm, and more. Filters noise, groups errors by rule, collapses repeats, and typically reduces token consumption by >90%. ~9ms overhead. YAML-configurable with layered config (global → project → CLI).

gloc — Local LLM Launcher

One command to launch Claude Code or Codex against a local LLM backend. Auto-detects LM Studio and Ollama, manages Ollama model lifecycle (pull, load, warmup), sets the right env vars, and execs into your CLI of choice. YAML-configurable with aliases, per-client env templates, and ordered backend priority.

Documentation

• gcode User Guide — search, symbols, dependency graphs, project management
• gsqz User Guide — pipelines, step types, configuration, debugging
• gloc User Guide — backends, clients, model management, configuration
• Changelog — release history
• gcode README — architecture and build details
• gsqz README — architecture and build details

Install

Pre-built binaries

Download from GitHub Releases. Binaries are available for macOS (ARM/x86), Linux (x86/ARM), and Windows (x86/ARM).

From crates.io

# gcode (with embeddings — requires cmake)
cargo install gobby-code

# gcode (with GPU acceleration — pick your backend)
cargo install gobby-code --features cuda    # NVIDIA (requires CUDA toolkit)
cargo install gobby-code --features vulkan  # Any GPU (requires Vulkan SDK)
cargo install gobby-code --features rocm    # AMD (requires ROCm)

# gcode (without embeddings)
cargo install gobby-code --no-default-features

# gsqz
cargo install gobby-squeeze

# gloc
cargo install gobby-local

On macOS, Metal GPU acceleration is enabled automatically. On Linux/Windows, embeddings use CPU inference by default — add a GPU feature flag for hardware acceleration.

From source

git clone https://github.com/GobbyAI/gobby-cli.git
cd gobby-cli
cargo install --path crates/gcode
cargo install --path crates/gsqz
cargo install --path crates/gloc

Development

cargo build --workspace --no-default-features   # Build all tools
cargo test --workspace --no-default-features    # Test all tools
cargo clippy --workspace -- -D warnings         # Lint all tools
cargo fmt --all --check                         # Check formatting

License

Apache 2.0 — see LICENSE.